Anàlisi estàtica i format
Anàlisi estàtica i format del codi
beautiful-prose
EricGrill
A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.
humanize
richtabor
Reviews and edits copy to remove AI-generated patterns and make text sound natural. Use when editing drafts, reviewing copy, "humanize this", "make it less AI", "sounds too AI", "remove AI patterns", "edit my copy", "this sounds robotic", or when text feels machine-generated.
outlining-wechat-tech-posts
alffei
Builds WeChat-friendly outlines for tech posts, including multi-level TOC, reader-benefit lines per section, pitfalls and action checklists, and 30-second skim summaries. Use when the user asks for outlines, structures, or tutorial-style blueprints for tech/engineering WeChat公众号.
bash-lint
Jamie-BitFlight
This skill should be used when the user asks to "lint bash script", "run shellcheck", "format shell script", "use shfmt", "fix shellcheck errors", or mentions shell script linting, formatting, code quality, or pre-commit hooks for bash.
holistic-linting
Jamie-BitFlight
Comprehensive linting and formatting verification workflows. Provides automatic format-lint-resolve pipelines for orchestrators and sub-agents. Use when running linters, fixing ruff/mypy/bandit errors, ensuring code quality before completion, or resolving linting issues systematically.
bad-faith-rhetoric-detector
curiositech
Analyze repeated non-engagement, deflection, motte-and-bailey shifts, tone policing, sealioning, and related manipulative discourse patterns. Use when the user suspects they are being rhetorically managed rather than answered, or when they need a careful pattern read grounded in quotes and alternatives. NOT for psychiatric diagnosis, legal judgment, or help deploying bad-faith tactics.
stakeholder-map
alunadev
"Builds a Power × Interest stakeholder map and generates a communication plan per quadrant. Use when managing a complex launch, aligning cross-functional teams, or preparing stakeholder engagement strategy. Triggers on: stakeholder management, stakeholder map, stakeholder alignment, communication plan, power interest grid, cross-functional alignment, executive alignment, managing up."
applying-react-native-best-practices
alunadev
React Native and Expo best practices for building performant mobile apps. Use this skill when building React Native or Expo applications, optimizing list performance with FlashList, implementing animations with Reanimated, configuring native modules, routing with expo-router, managing state in mobile contexts, or working in monorepo setups with Expo. Apply proactively when writing FlatList, useEffect for animations, TouchableOpacity, or setting up navigation — these patterns prevent common mobile performance pitfalls.
prompt-engineering-patterns
alunadev
A library of reusable, production-tested prompt engineering patterns for building AI-powered features. Use when designing system prompts for apps, building AI pipelines, selecting the right prompting technique for a use case, or reviewing prompts for common failure modes. Complements the prompt-engineering skill (which covers the optimization framework); this skill covers the pattern library itself.
redash
jwmossmoz
Query Mozilla's Redash (sql.telemetry.mozilla.org) for telemetry data from BigQuery. Use when querying Firefox user telemetry, OS distribution, architecture breakdown, or running custom SQL against Mozilla's data warehouse. Triggers on "redash", "telemetry query", "sql.telemetry", "BigQuery query", "Firefox data", "client counts", "user population", "DAU", "MAU", "macOS version", "macOS distribution", "Apple Silicon", "aarch64", "x86_64", "architecture distribution", "Windows version", "Windows distribution", "how many users", "what share of users", "what percentage of Firefox users".
prompt-generator
genfeedai
Generate optimized prompts for AI image and video generation. Triggers on "generate a prompt for", "write me a prompt", "create an image prompt", "create a video prompt", "optimize this prompt".
figma-reader
delexw
Read Figma designs via Figma MCP server. Auto-detects MCP availability and prompts user only if setup is needed. Use when Figma links or UI design images are found in task context.
editor
dangeles
Use when documents need prose improvement, CLAUDE.md style enforcement (prose over bullets, bridging transitions, complete sentences), or final polish before archival
essay-voice-matcher
dangeles
Use when written text needs evaluation against a user's writing style profile and sample essays for voice consistency during essay pipeline execution.
claude-md-authoring
ratacat
Creates and reviews CLAUDE.md configuration files for Claude Code. Applies HumanLayer guidelines including instruction budgets (~50 user-level, ~100 project-level), WHAT/WHY/HOW framework, and progressive disclosure. Identifies anti-patterns like using Claude as a linter for style rules.
every-style-editor-2
ratacat
Use this agent when you need to review and edit text content to conform to Every's specific style guide. This includes reviewing articles, blog posts, newsletters, documentation, or any written content that needs to follow Every's editorial standards. The agent will systematically check for title case in headlines, sentence case elsewhere, company singular/plural usage, overused words, passive voice, number formatting, punctuation rules, and other style guide requirements.
ralph-gpu
vercel-labs
Minimal WebGPU shader library for creative coding and real-time graphics. Provides fullscreen passes, particles, compute shaders, render targets, and ping-pong buffers with automatic uniform bindings and global time/resolution tracking.
every-style-editor
ratacat
This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.
gemini-imagegen
ratacat
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
me:devis-xlsx
kbrdn1
Construit un classeur de devis .xlsx paramétrable à partir d'une estimation de charge en jours-homme : onglet paramètres (TJM, TVA, sélecteurs en cellules jaunes), onglet d'estimation détaillée avec sous-totaux par formule, fourchettes bas–haut, scénarios ou toggles de périmètre, buffer de risque, et onglet Notes documentant les écarts et hypothèses. À utiliser dès que l'utilisateur veut transformer une estimation de charge en devis chiffré (xlsx / Google Sheets), ou qu'il emploie « deviser », « chiffrage », « devis », « TJM », « jours-homme », « classeur de devis », ou demande « la même chose » après avoir fourni une estimation Claude Code, un audit de repos ou un journal de charge. Couvre les prestations de dev (back/front), la maintenance/support, les évolutions et les projets multi-lots avec reversements. Utiliser cette skill plutôt que d'inventer un format de devis ou un TJM, même si l'utilisateur ne dit pas explicitement « skill » ou « template ».
aio-golang-mastery
aiocean
Complete Go development skill covering idiomatic patterns, error handling, concurrency, interfaces, generics, testing (TDD, fuzzing, benchmarks), project structure, production hardening, and gRPC. Based on Google Go Style Guide, Uber Go Style Guide, Effective Go. Updated for Go 1.25. Use when writing, reviewing, or refactoring Go code, building HTTP/gRPC servers, designing concurrent systems, or optimizing performance.
oneshot
kbrdn1
Ultra-fast feature implementation - Explore then Code then Test
output-formats
kbrdn1
Skill migrated from _fragments/base/output-formats
training-data-curation
M4n5ter
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.